Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false and destructiveHint=true; the description adds real behavioral context beyond them — the created fact's shape (follow_up_at plus optional note), its graph connection to the target object, and the important limitation that follow-ups cannot be read back through a dedicated tool yet. It stops short of saying whether the follow-up can later be edited, deleted, or re-set, and the additive 'creates a fact' framing sits somewhat awkwardly against destructiveHint=true.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the action and an example before the data-shape and interim-workaround details. The final sentence is long but every clause carries needed information about the missing read path; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no output schema, the description covers what is created, required inputs, and the notable absence of a read-back tool with a concrete workaround. It omits what the call returns (created fact id/shape) and whether re-setting an existing follow-up overwrites or duplicates it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description still adds meaning: 'when' is ISO 8601 and 'usually in the future' (implying past dates are legal), 'note' is optional reminder text, and 'about_object_id' is the object the follow-up is attached to. The mapping of description fields (follow_up_at) to the schema parameter name ('when') is slightly indirect but inferable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb + resource ('Set a dated follow-up about an object in the user's graph') with a concrete natural-language example ('follow up with Jane in March') and a precise statement of what it creates (a follow-up fact with follow_up_at, optional note, connected to the object). This clearly separates it from generic siblings like create_graph_object or record_interaction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly describes the read-side workflow and names the alternative ('list the user's fact objects and filter on json_data.follow_up_at yourself') because no dated query tool exists. It does not, however, say when to prefer this over record_interaction or create_graph_object for the write side, so the when-not guidance is incomplete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.